Academic Personal Homepage

The official repo of the paper: delta-Mem: Efficient Online Memory for Large Language Models

A platform for reproducible world model research and evaluation

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

This is the official implementation of the paper "ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy".

Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.

Official Implementation of Dyn-O: Building Structured World Models with Object-Centric Representations (NeurIPS 2025)

An official code repo of paper Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints.

EO: Open-source Unified Embodied Foundation Model Series

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

Official code for paper "Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"

Fully open reproduction of DeepSeek-R1

No fortress, purely open ground. OpenManus is Coming.

The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability"

This is the official implementation of paper "Leveraging Dual Process Theory in Language Agent Framework for Simultaneous Human-AI Collaboration."

A collection of awesome public projects about LLM Safety.

Self-playing Adversarial Language Game Enhances LLM Reasoning, NeurIPS 2024

Official implementation of paper on Nature Machine Intelligence: "Preserving and Combining Knowledge in Robotic Lifelong Reinforcement Learning"